{"paper_id":"2411.05801","title":"Do LLM Personas Dream of Bull Markets? Comparing Human and AI Investment Strategies Through the Lens of the Five-Factor Model","authors":["Harris Borman","Anna Leontjeva","Luiz Pizzato","Max Kun Jiang","Dan Jermyn"],"paper_date":"2024-10-28","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2411.05801v1","page_url":"https://thequant.space/flowcharts/do-llm-personas-dream-of-bull-markets-comparing-human-and-a/","scores":{"empirical_rigor":6.5,"math_complexity":3.5,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper investigates whether LLM-powered personas can reliably interpret the five-factor personality model and map traits into investment‑related behaviours consistent with human research.","quote":"In this study, we investigated whether an LLM persona with a specific Big Five personality profile would perform an investment task similarly to a human with the same personality traits. This study aims to address this limitation by investigating if LLM-powered personas 1 can reliably interpret a human personality model (specifically the five-factor model) and map personality traits into specific behaviours that are","summary":"Large Language Models (LLMs) have demonstrated the ability to adopt a personality and behave in a human-like manner. There is a large body of research that investigates the behavioural impacts of personality in less obvious areas such as investment attitudes or creative decision making. In this…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Personas are given only personality trait information and no additional demographic or contextual data.","type":"model","stated":"explicit","quote":"Prompts were constructed to have only information about the persona’s personality traits with no extra information provided (See Appendix A for prompt).","support":"full"},{"assumption":"Ordinary least squares regression is appropriate for identifying correlations between personality traits and behaviours.","type":"statistical","stated":"explicit","quote":"For both tests we used an ordinary least squares (OLS) regression to identify correlations between personality traits and each desired behaviour.","support":"full"}]},"datasets":{"status":"available","items":[{"name":"Behavioural survey","provider":null,"kind":"synthetic","access":"proprietary","period":null,"universe":null,"quote":"2.2 Behavioural survey To measure if personas can correctly associate personality with behaviour, we constructed a simple behavioural survey.","support":"full"},{"name":"Investment simulation","provider":null,"kind":"synthetic","access":"proprietary","period":null,"universe":null,"quote":"2.3 Investment simulation To determine if LLMs were interpreting their personality traits to produce different behaviours, as opposed to simply learning the expected answer to each question during training, we constructed a simple investment task.","support":"full"}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"unclear"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"none","findings":[{"finding":"LLM personas accurately reflect human personality in learning style, impulsive decision making and risk appetite, but cannot reliably represent environmental attitudes.","kind":"performance","quote":"We found that LLMs can accurately reflect a human personality in the areas of learning style, impulsive decision making and risk appetite while environmental attitudes could not be reliably interpreted.","support":"full"},{"finding":"Personas produce more accurate human‑like behaviour in a simulated investment task than when answering survey questions.","kind":"performance","quote":"We observed that in all these cases LLM personas produced a more accurate simulation of human behaviour when performing a simulated task compared to answering questions in a survey.","support":"full"},{"finding":"During training LLMs learn associations between personality traits and behaviours, enabling generalisation to novel simulated tasks.","kind":"theoretical","quote":"The observed behaviour suggests that during the training process the LLM has learnt to make associations between personality traits and behaviours themselves allowing them to produce an accurate representation of human behaviour in these areas when operating in a simulated environment.","support":"full"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":8,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":2,"extracted_at":"2026-11-14T19:54:18Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}